....let us not forget the type of 'business' contracts companies like
Intel, M$, etc... force others to pen. Just because some of these
companies are not selling equipment with AMD chips, does not
necessarily imply the quality of the chip is poor. This would be a
sufficient condition, but not necessary.
DK
From: [EMAIL PROTECTED] AT INTERNET on 05/22/2001 04:51 PM
To: Douglas Knudsen/ATL/ALLTELCORP, [EMAIL PROTECTED] AT
INTERNET@CCMAIL
cc:
Subject: RE: Benchmarks
Truth and reality, if AMD really was that much better, or even fairly
close,
in server performance and stability, don't you think that businesses
that
make millions of dollars selling these machines, i.e. Dell, Compaq,
and HP,
would start selling AMD superservers. I haven't seen it yet and until
I do
anyone can run any test they want, but years of experience and actual
work
load tests will keep me with Intel for now! The price is very small
trade
in the grand picture!
CW
-----Original Message-----
From: Steve [mailto:[EMAIL PROTECTED]]
Sent: Tuesday, May 22, 2001 2:21 PM
To: CF-Server
Subject: Re: Benchmarks
What I mean't was actually encoding the video straight from the
tape to
hdd. Using realProducer or windows media encoder. For serving out
the
video that is different. What I was going to get at is that the AMD
chip
speed seems more burstable while the Pentium chips are consistent.
Kind of
like DSL. For example try running AMD chips on a SQL server vs. a
Pentium
server. The AMD server might respond sometimes faster on queries but
othertimes very slow, it might even look like the server has locked up
at
certain times. This can make troubleshooting the less expensive
server very
difficult. On the other hand the sql server with the pentium chips
will run
very consistently with the queries, even if you get enough traffic to
set
the processors at 100% the machine would not appear to be locked up.
I put
down video encoding in my first response because I believe that is the
easiest way to measure processor performance.
Steve
----- Original Message -----
From: "Jon Hall" <[EMAIL PROTECTED]>
To: "CF-Server" <[EMAIL PROTECTED]>
Sent: Tuesday, May 22, 2001 12:42 PM
Subject: Re: Benchmarks
> I would agree that if you need to do lots of live video encoding
for a
web
> site, a P4 is probably by far the best solution. I current have a
site
that
> handles 10 live encoded asf streams on a Dual P3 fine though. It's
not
> hurting yet.
> However the majority of us do not encode video on our web and
database
> servers which is why I posted to CF-Server, not a video editing
list.
>
> I think though the biggest place I'd notice the difference is my
pocketbook.
> A $2000 machine beat a $8000 one. I think I'd wait that extra few
seconds
if
> I ever encoded some video.
>
> jon
> ----- Original Message -----
> From: "Steve" <[EMAIL PROTECTED]>
> To: "CF-Server" <[EMAIL PROTECTED]>
> Sent: Tuesday, May 22, 2001 11:31 AM
> Subject: Re: Benchmarks
>
>
> > I promise you that you can tell the difference if you are doing
video
> > encoding.
> >
> > Steve
> >
> >
> > ----- Original Message -----
> > From: "Jon Hall" <[EMAIL PROTECTED]>
> > To: "CF-Server" <[EMAIL PROTECTED]>
> > Sent: Tuesday, May 22, 2001 4:14 AM
> > Subject: Benchmarks
> >
> >
> > > I thought I'd post some very interesting benchmarks that I
suspected
to
> be
> > the case, but never have been able to confirm it myself. These are
> > especially enlightening to me because of the seemingly blind
adherance
to
> > Intel in the server world that we are a part of.
> > > AnandTech recently did a review of the new Dual P4 Xeon's. One
benchmark
> > was partcularily interesting.
> > > They recorded a 30 minute transaction log of their forums, which
runs
> > FuseTalk. During the 30 minute recording there were: 105267
selects,
4984
> > updates, 701 inserts and 5 deletes performed on the database. They
then
> ran
> > the transaction logs on each of the platforms they tested.
> > >
> > > Heres what they found:
> > >
> > > Dual P4 Xeon 1.7 GHZ
> > > 14m 49s
> > > Dual P3 933 MHz
> > > 22m 34s
> > > Single P4 Xeon 1.7GHZ
> > > 22m 31s
> > >
> > > and the shocker
> > >
> > > Single AMD Athlon 1.2 Ghz
> > > 18m 6s
> > >
> > > Here is a link to the article:
> > > http://www.anandtech.com/showdoc.html?i=1472
> > >
> > > Considering the huge price gap between a dual P3 and a run of
the mill
> > Athlon this seems incredible to me.
> > >
> > > My only comment wuold be, the next time you throw money at a
problem.
> You
> > might want to throw it in the right direction!
> > >
> > > I cant say how many times, the Intel drones in this industry
have
> > questioned me when I in passing mention that I only use AMD chips.
It
just
> > comes down to price for me, but now I can stand on firm ground and
tell
> them
> > to go waste their money!
> > > Of course, someone will eventually try to pull the reliability
card.
It
> > will be of no use, I have had ammo there for a while now.
> > >
> > > jon
> > >
> > >
> > >
> >
>
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Structure your ColdFusion code with Fusebox. Get the official book at
http://www.fusionauthority.com/bkinfo.cfm
------------------------------------------------------------------------------
To unsubscribe, send a message to [EMAIL PROTECTED] with
'unsubscribe' in the body or visit the list page at www.houseoffusion.com
